Agent skill

Strategy

by EliasOulkadi in EliasOulkadi/shokunin

Run structured brainstorming sessions (divergent/convergent), improve prompts with 7-dimension framework, and apply decision frameworks (RICE, weighted scoring, first principles, pre-mortem).

MITAuto-check passedAgent Workflows

Install Strategy

skills CLI
$ npx skills add EliasOulkadi/shokunin --skill strategy -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install EliasOulkadi/shokunin strategy --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/EliasOulkadi/shokunin.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.pack/skills/strategy .claude/skills/strategy && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
strategy
GitHub stars
114
Token cost
~2.9k tokens
SKILL.md length
1,338 words
Files
1
Skills in repo
49
Repo updated
First seen
Licence
MIT

At a glance

Run structured brainstorming sessions (divergent/convergent), improve prompts with 7-dimension framework, and apply decision frameworks (RICE, weighted scoring, first principles, pre-mortem).

  • Works in 10 steps: Intake & Framing → Select Framework → Execute Framework → …
  • Tasks that involve Brainstorming
  • SKILL.md covers Workflow, Brainstorming, Decision Frameworks and Prompt Engineering, plus 4 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Strategy is an agent skill from EliasOulkadi/shokunin. Run structured brainstorming sessions (divergent/convergent), improve prompts with 7-dimension framework, and apply decision frameworks (RICE, weighted scoring, first principles, pre-mortem).

Its SKILL.md is about 2.9k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts. Compatibility notes: opencode

It sits in Agent Workflows, covering Brainstorming and Prioritization frameworks. The repository describes itself as: 職人 Shokunin 62 AI agent skills for OpenCode, Claude Code, Cursor, Windsurf. ChromaDB memory, MCP servers, declarative self-updates. Multi-model, open source, zero cost. The licence is MIT.

When your agent uses it

  • Tasks that involve Brainstorming
  • Tasks that involve Prioritization frameworks

Example prompts

  • “/strategy”

Requirements

  • Compatibility (from SKILL.md): opencode

Workflow steps

10 steps, taken from the step headings in SKILL.md.

  1. Intake & Framing
  2. Select Framework
  3. Execute Framework
  4. Document & Deliver
  5. Verify Against Production Checklist
  6. Process
  7. Divergent Techniques
  8. Convergent Techniques
  9. Session Template
  10. Session Ground Rules

What it can do on your machine

Read from SKILL.md and the folder at commit 4c68e5b. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

  • Compatibility

    opencode

    From compatibility in the SKILL.md frontmatter.

Context cost

Strategy loads about 2.9k tokens when it runs. Until then it costs about 50 tokens; SKILL.md has 1,338 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~50
When it runs · the whole SKILL.md, loaded when a task matches
~2.9k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from EliasOulkadi/shokunin at commit 4c68e5b, republished under its MIT licence (© EliasOulkadi). 1,338 words, ~2,946 tokens.

Download SKILL.mdSave it as .claude/skills/strategy/SKILL.md (or your agent's skills folder).
name
strategy
description
Run structured brainstorming sessions (divergent/convergent), improve prompts with 7-dimension framework, and apply decision frameworks (RICE, weighted scoring, first principles, pre-mortem).
compatibility
opencode
triggers
brainstorm ideas, run an ideation session, improve a prompt, write a better prompt, make decisions, strategic thinking, how to decide between options, prompt…
negatives
creative direction (use brand-design skill), content strategy (use content-marketing), personal coaching, simple yes/no decisions without tradeoffs, design…
license
MIT
metadata.workflow
strategy
metadata.audience
developers
metadata.version
3.0.0

Strategy

Structured thinking for brainstorming, prompt engineering, and decision making.

Workflow

Step 1: Intake & Framing

Extract the user's core need and classify it into one of three tracks:

TrackTriggerOutput
Decision"Should I...", "Which option...", "Help me choose..."Scored recommendation with rationale and runner-up tradeoff
Ideation"Brainstorm...", "Generate ideas for...", "What are ways to..."Prioritized list of ideas with convergent selection
Clarity"How do I think about...", "Improve this prompt", "Reframe..."Restructured framing, 7-dimension prompt, or first-principles breakdown

If the user's need spans multiple tracks, run them sequentially: Clarity → Ideation → Decision.

Step 2: Select Framework

For Decision track: Choose ICE if speed matters, Impact/Effort matrix if resources are constrained, First Principles if the problem feels stuck or assumed, Pre-Mortem if the decision is high-stakes and irreversible.

For Ideation track: Start with brainwriting (quantity). If ideas stall, inject SCAMPER or reverse brainstorming. Never open with free association for groups of 3+ — dominant voices take over.

For Clarity track: Run the 7-dimension prompt diagnosis. Identify which dimensions are weak (0-3 on a 1-10 scale). Rewrite the prompt addressing the weakest dimensions first.

Step 3: Execute Framework

Follow the framework protocol from its dedicated section below. Timebox strictly:

  • Decision: 20 min (5 min framing, 10 min scoring, 5 min decision)
  • Ideation: 60 min (divergent 30 min, cluster 10 min, convergent 20 min)
  • Clarity: 10 min (diagnose 3 min, rewrite 5 min, changelog 2 min)
Step 4: Document & Deliver

Every strategy output must include:

  • The chosen framework and why it was selected
  • The raw output (scores, ideas, rewritten prompt)
  • One recommended action with owner + next step + deadline
  • One explicitly rejected alternative and the reason
Step 5: Verify Against Production Checklist

Run the Production Checklist before delivering. If any item is unchecked, return to the relevant step. Never deliver a strategy artifact that skips convergent selection or lacks a specified output format.

Brainstorming

1. Process
  1. Divergent (generate, no judgment) — 15-30 min
  2. Clustering (organize, group, eliminate) — 10-15 min
  3. Convergent (select, vote, prioritize) — 15-20 min

Never mix divergent and convergent — judgment kills ideas before they form.

2. Divergent Techniques
TechniqueHowBest for
Free associationWrite everything, no filterWarm-up, quantity
Brainwriting 6-3-56 people write 3 ideas in 5 min, passAvoiding dominant voices
Reverse brainstormingHow to make it worse? Then reverse.Breaking assumptions
Random wordRandom noun → force connectionsLateral thinking
SCAMPERSubstitute, Combine, Adapt, Modify, Put to use, Eliminate, ReverseSystematic exploration
HMWReframe as "How Might We" questionsDesign thinking
Worst ideaGenerate terrible ideas, then invertReducing fear
3. Convergent Techniques
TechniqueHow
Dot voting3-5 votes per person
Impact/effort matrixX: impact, Y: effort
ICE scoringImpact, Confidence, Ease (1-10, average)
NUF testNew, Useful, Feasible (1-10 each)
4. Session Template
PhaseDurationActivity
Problem framing10 minDefine "How might we..." question
Warm-up5 minLow-stakes exercise
Divergent round 115 minBrainwriting. Target: 30+ ideas
Cluster10 minAffinity mapping
Divergent round 210 minSCAMPER on strongest clusters
Convergent15 minImpact/effort matrix. Top 3-5
Action planning10 minOwner, next step, deadline
5. Session Ground Rules
  • Defer judgment. Go for quantity (set targets: "50 ideas in 20 min")
  • One conversation at a time. Build on "Yes, and..."
  • Encourage wild ideas. Round-robin or brainwriting.
  • Hard stop at 90 min.

Decision Frameworks

ICE Scoring
Score = Impact (1-10) × Confidence (1-10) × Ease (1-10)
Higher = prioritize first
Impact/Effort Matrix
           High Impact          Low Impact
Low Effort  → Do First         → Quick Wins
High Effort → Strategic        → Don't Do
First Principles Thinking
  1. Identify the current belief/assumption
  2. Break it down into fundamental truths
  3. Rebuild from those truths
Current: "Our testing takes too long to run"
Deconstruction: What IS testing? Verifying code behavior.
Fundamental: We need confidence code works. Speed matters but accuracy matters more.
Rebuild: What's the fastest way to get accuracy confidence? Change test scope to integration-focused.
Pre-Mortem Analysis

Before starting a project, imagine it failed 6 months from now:

  1. What went wrong? (list 5-10 failure modes)
  2. For each, what's the probability? (low/medium/high)
  3. For each, what's the impact? (minor/major/critical)
  4. Mitigation: What can we do NOW to prevent it?
Opportunity Cost
Choosing Option A means NOT choosing Options B-Z.
Before committing, list: What else could these resources do?

Prompt Engineering

The 7 Dimensions
  1. Clarity — Remove ambiguity. Every noun and verb should have one interpretation.
  2. Specificity — Replace vague language with concrete details. Use names, paths, numbers.
  3. Constraints — Technology, resource, time, compliance hard boundaries.
  4. Format — Bullet list, table, code block, JSON, Mermaid. Tell the model how to answer.
  5. Examples — One example is worth 100 words of description.
  6. Tone — Internal message (direct), client email (professional-cordial), docs (neutral-precise), bug report (factual-minimal).
  7. Iteration Signal — "Start here, refine later" vs "Production-ready" vs "Give me options" vs "Just the code"
Enhancement Workflow
  1. Diagnose: Run through 7 dimensions — identify which are weak or missing
  2. Rewrite: Complete rewrite, don't annotate original
  3. Changelog: 1-2 bullet points per dimension improved
Specificity Table
VagueSpecific
"help with this code""refactor auth middleware in src/middleware/auth.ts"
"some options""exactly 3 options ranked by cost"
"make it better""improve load time from 3s to <1s on mobile Chrome"
"explain""explain in 3 bullet points to a junior dev"
Show full SKILL.md (554 more words)Show less

Error Handling

ErrorCauseResolution
Session runs over 90 minPoor timeboxingAssign a timer. Hard stop at 90 min regardless of progress
Dominant voice dominatesNo facilitation structureSwitch to brainwriting or round-robin. No open floor until last 10 min
Ideas too similar / not novelGroupthinkInsert reverse brainstorming or random-word technique mid-session
No clear decision after convergent phaseTie votesUse ICE scoring as tiebreaker. Default to impact if still tied
Prompt still produces bad output after rewriteDiagnosed wrong dimensionRe-run 7-dimension check. Most often: missing constraint or missing example
"I don't have ideas" blockBlank-page problemUse worst-idea technique or reverse brainstorming to unstick

Production Checklist

Before delivering a strategy artifact (session output, prompt, decision document):

  • Problem statement defined in "How might we..." format
  • Divergent and convergent phases kept separate with a clear transition
  • Convergent selection uses at least one scoring method (ICE, impact/effort, dot voting)
  • Prompt covers all 7 dimensions — no dimension is "N/A" without reason
  • Prompt includes at least one example (dimension 5)
  • Output format specified in prompt (dimension 4)
  • Iteration signal included (dimension 7)
  • Decision documented with rationale and runner-up tradeoff
  • Action items: owner + next step + deadline

Anti-Patterns

Anti-PatternWhy It FailsCorrection
Mixed divergent and convergentJudgment kills idea generation before it startsSeparate phases with a break. No "yes but" during divergent
No warm-upCold start produces safe, boring ideasAlways do 5-min warm-up (e.g. "ideas for improving a paperclip")
Dominant voices take overJunior or quiet team members disengageUse brainwriting, round-robin. No open discussion until convergent
Too many people (8+)Diffusion of responsibility, not enough airtime4-8 max per session. Split into parallel groups if larger team
No follow-throughGreat ideas die after the sessionAssign ownership, next step, and deadline before closing
Prompt too short (<10 words)Model fills gaps with wrong assumptionsExpand to cover context, constraint, format, and example
Compound requestModel optimizes for first instruction onlySplit into separate prompts or use numbered list with weighting
No output formatModel chooses — rarely the most useful oneAlways specify format (JSON, table, bullet list, code block)
Using ICE without confidence checkFalse precision — confidence is often guessedCalibrate confidence: "how sure are you on a 1-10?" and average across 3 people
Skipping opportunity costOvercommit to first good optionBefore finalizing, ask: "What else could these resources do?"

Advanced Decision Frameworks

RICE Scoring

Score features: Score = (Reach * Impact * Confidence) / Effort

  • Reach: how many users affected (1-1000+)
  • Impact: 0.25 (minimal), 0.5 (low), 1 (medium), 2 (high), 3 (massive)
  • Confidence: 20% (gut), 50% (some data), 80% (quantified), 100% (A/B tested)
  • Effort: person-months
Kano Model

Classify features: Basic (expected, absence = dissatisfaction), Performance (more = better), Delighter (unexpected, absence = neutral). Prioritize: Basic → Performance → Delighter.

OKR-to-Task Decomposition
  • Objective: qualitative, inspiring, time-bound (quarter)
  • Key Results: 3-5 quantitative outcomes
  • Tasks: decompose each KR into 2-3 actionable tasks per week

Sources

  • Alex Osborn "Applied Imagination"
  • IDEO design thinking
  • d.school Stanford facilitation guides
  • Jake Knapp "Sprint"
  • Annie Duke "Thinking in Bets"
  • First Principles (Elon Musk / Richard Feynman approach)
  • Fermi Estimation techniques

Checklist

  • Skill loads without errors in the AI agent
  • YAML frontmatter is valid (description, compatibility, audience)
  • Workflow section provides clear step-by-step instructions
  • Error handling section covers common failure modes
  • All referenced files (references/, scripts/, assets/) exist
  • Skill triggers correctly for intended use cases
  • No broken links or missing resources

© EliasOulkadi, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in .pack/skills/strategy of EliasOulkadi/shokunin.

Open the folder on GitHubat commit 4c68e5b

Compare with similar skills

Strategy next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Strategy compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Strategy this skillEliasOulkadi/shokunin114—~2.9kAutomated safety check: PassMIT
Pm Brainstormserejaris/personal-corp-os229—~2.1kAutomated safety check: PassMIT
Brainstormingobra/superpowers297k1 repos~2.5kAutomated safety check: PassMIT
Brainstormingxpinjection/test-driven-spring-boot11253 repos~2.6kAutomated safety check: PassMIT
Yao Meta Skillyaojingang/yao-meta-skill2.7k—~768Automated safety check: PassMIT
Typesafe AIOpenAgentsInc/openagents4559 repos~2.5kAutomated safety check: PassMIT

Similar skills

  • Pm Brainstorm

    serejaris/personal-corp-os

    Проводит структурированный сеанс дивергенции вокруг конкретной продуктовой проблемы или возможности.

    229 GitHub stars~2.1k tokensUpdated 3 days ago
    Agent WorkflowsAuto-check passed
  • Brainstorming

    obra/superpowers

    Makes the agent clarify intent and agree on a design with you before writing any code, scaling the process from a quick spike to a written spec.

    297k GitHub starsUsed in 1 repo~2.5k tokens
    Agent WorkflowsAuto-check passed
  • Brainstorming

    xpinjection/test-driven-spring-boot

    You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior.

    112 GitHub starsUsed in 53 repos~2.6k tokens
    Agent WorkflowsAuto-check passed
  • Yao Meta Skill

    yaojingang/yao-meta-skill

    Create, improve, or evaluate an existing skill from workflows, prompts, SOPs, scripts.

    2.7k GitHub stars~768 tokensUpdated 1 mo ago
    Agent WorkflowsAuto-check passed
  • Typesafe AI

    OpenAgentsInc/openagents

    Build AI-powered software with TypeSafe: small units of AI intelligence you can use like programming primitives.

    455 GitHub starsUsed in 9 repos~2.5k tokens
    Agent WorkflowsAuto-check passed
  • Trellis Start

    ROYIANS/foliq-print-template-designer

    Initializes an AI development session by reading workflow guides, developer identity, git status, active tasks, and project guidelines from .trellis/.

    136 GitHub starsUsed in 6 repos~646 tokens
    Agent WorkflowsAuto-check passed

More from EliasOulkadi/shokunin

All 49 skills in this repo
  • CI CD

    EliasOulkadi/shokunin

    Design CI/CD pipelines for GitHub Actions, GitLab CI, and CircleCI with matrix builds, test sharding, caching, Docker layer caching, OIDC auth, deployment strategies (rolling, blue-green, canary)…

    114 GitHub stars~3.4k tokensUpdated 6 days ago
    Auto-check: notes
  • Component Forge

    EliasOulkadi/shokunin

    Build production-grade components for React, Vue 3, and Svelte 5 with all states (loading, empty, error, success, idle), TypeScript strict, WCAG 2.2 accessibility, server components (RSC), and…

    114 GitHub stars~3.6k tokensUpdated 6 days ago
    Auto-check: notes
  • DB Admin

    EliasOulkadi/shokunin

    PostgreSQL database administration — backup/restore (pgdump, PITR, WAL archiving), health monitoring (connections, bloat, cache hit ratio, dead tuples), connection pooling (PgBouncer), replication…

    114 GitHub stars~2k tokensUpdated 6 days ago
    Auto-check: notes
  • DB Sculptor

    EliasOulkadi/shokunin

    Design database schemas with Prisma/Drizzle, PostgreSQL index strategy (B-tree, GIN, GiST, BRIN, Hash), query optimization (EXPLAIN ANALYZE), migration safety (expand/contract, zero-downtime), and…

    114 GitHub stars~3.1k tokensUpdated 6 days ago
    Auto-check: notes
  • Docker

    EliasOulkadi/shokunin

    Optimize Docker images with multi-stage builds, distroless bases, BuildKit cache mounts, multi-arch builds, compose watch, security hardening (non-root, seccomp, capabilities drop), and…

    114 GitHub stars~3.8k tokensUpdated 6 days ago
    Auto-check: notes
  • Error Handler

    EliasOulkadi/shokunin

    Design error handling, structured logging, and observability with OpenTelemetry (traces, metrics, logs), error classification, recovery patterns (retry with jitter, circuit breaker, bulkhead…

    114 GitHub stars~3.6k tokensUpdated 6 days ago
    Auto-check: notes

Categories

Questions about Strategy

What does Strategy do?

Run structured brainstorming sessions (divergent/convergent), improve prompts with 7-dimension framework, and apply decision frameworks (RICE, weighted scoring, first principles, pre-mortem). Strategy is an agent skill from EliasOulkadi/shokunin. Run structured brainstorming sessions (divergent/convergent), improve prompts with 7-dimension framework, and apply decision frameworks (RICE, weighted scoring, first principles, pre-mortem).

When should I use Strategy?

Strategy fits situations like: tasks that involve Brainstorming; tasks that involve Prioritization frameworks.

How do I install Strategy in Claude Code?

Run `npx skills add EliasOulkadi/shokunin --skill strategy -a claude-code`. Or copy the skill folder (.pack/skills/strategy in EliasOulkadi/shokunin) into .claude/skills/strategy in your project. Claude Code loads it when a task matches its description.

How do I install Strategy in Codex?

Run `npx skills add EliasOulkadi/shokunin --skill strategy -a codex`. Or copy the skill folder (.pack/skills/strategy in EliasOulkadi/shokunin) into .agents/skills/strategy in your project. Codex loads it when a task matches its description.

Can I use Strategy in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add EliasOulkadi/shokunin --skill strategy -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/strategy, .gemini/skills/strategy, .github/skills/strategy and .opencode/skills/strategy in your project.

What does Strategy need to run?

SKILL.md names no scripts, command-line tools or credentials: Strategy is instructions for the agent only. Compatibility (from SKILL.md): opencode.

Does Strategy access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Strategy safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Strategy use?

Strategy is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Strategy use?

About 2.9k tokens (SKILL.md is roughly 12k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Strategy?

Skills that share tags, products or a category with Strategy: Pm Brainstorm (serejaris/personal-corp-os, 229 stars), Brainstorming (obra/superpowers, 297k stars), Brainstorming (xpinjection/test-driven-spring-boot, 112 stars) and Yao Meta Skill (yaojingang/yao-meta-skill, 2.7k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Strategy?

EliasOulkadi (a GitHub user) maintains it in EliasOulkadi/shokunin, which has 114 GitHub stars. The repository holds 49 skills in this directory. The repository was last updated on October 5, 2026.

Source: EliasOulkadi/shokunin on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.